LoGU: Long-form Generation with Uncertainty Expressions

While Large Language Models (LLMs) demonstrate impressive capabilities, they still struggle with generating factually incorrect content (i.e., hallucinations). A promising approach to mitigate this issue is enabling models to express uncertainty when unsure. Previous research on uncertainty modeling has primarily focused on short-form QA, but realworld applications often require much longer responses. In this work, we introduce the task of Long-form Generation with Uncertainty(LoGU). We identify two key challenges: Uncertainty Suppression, where models hesitate to express uncertainty, and Uncertainty Misalignment, where models convey uncertainty inaccurately. To tackle these challenges, we propose a refinement-based data collection framework and a two-stage training pipeline. Our framework adopts a divide-and-conquer strategy, refining uncertainty based on atomic claims. The collected data are then used in training through supervised fine-tuning (SFT) and direct preference optimization (DPO) to enhance uncertainty expression. Extensive experiments on three long-form instruction following datasets show that our method significantly improves accuracy, reduces hallucinations, and maintains the comprehensiveness of responses.

Atomic Calibration of LLMs in Long-Form Generations

Large language models (LLMs) often suffer from hallucinations, posing significant challenges for real-world applications. Confidence calibration, which estimates the underlying uncertainty of model predictions, is essential to enhance the LLMs' trustworthiness. Existing research on LLM calibration has primarily focused on short-form tasks, providing a single confidence score at the response level (macro calibration). However, this approach is insufficient for long-form generations, where responses often contain more complex statements and may include both accurate and inaccurate information. Therefore, we introduce atomic calibration, a novel approach that evaluates factuality calibration at a fine-grained level by breaking down long responses into atomic claims. We classify confidence elicitation methods into discriminative and generative types and demonstrate that their combination can enhance calibration. Our extensive experiments on various LLMs and datasets show that atomic calibration is well-suited for long-form generation and can also improve macro calibration results. Additionally, atomic calibration reveals insightful patterns in LLM confidence throughout the generation process.

On the Transformations across Reward Model, Parameter Update, and In-Context Prompt

Despite the general capabilities of pre-trained large language models (LLMs), they still need further adaptation to better serve practical applications. In this paper, we demonstrate the interchangeability of three popular and distinct adaptation tools: parameter updating, reward modeling, and in-context prompting. This interchangeability establishes a triangular framework with six transformation directions, each of which facilitates a variety of applications. Our work offers a holistic view that unifies numerous existing studies and suggests potential research directions. We envision our work as a useful roadmap for future research on LLMs.

On the Worst Prompt Performance of Large Language Models

The performance of large language models (LLMs) is acutely sensitive to the phrasing of prompts, which raises significant concerns about their reliability in real-world scenarios. Existing studies often divide prompts into task-level instructions and case-level inputs and primarily focus on evaluating and improving robustness against variations in tasks-level instructions. However, this setup fails to fully address the diversity of real-world user queries and assumes the existence of task-specific datasets. To address these limitations, we introduce RobustAlpacaEval, a new benchmark that consists of semantically equivalent case-level queries and emphasizes the importance of using the worst prompt performance to gauge the lower bound of model performance. Extensive experiments on RobustAlpacaEval with ChatGPT and six open-source LLMs from the Llama, Mistral, and Gemma families uncover substantial variability in model performance; for instance, a difference of 45.48% between the worst and best performance for the Llama-2-70B-chat model, with its worst performance dipping as low as 9.38%. We further illustrate the difficulty in identifying the worst prompt from both model-agnostic and model-dependent perspectives, emphasizing the absence of a shortcut to characterize the worst prompt. We also attempt to enhance the worst prompt performance using existing prompt engineering and prompt consistency methods, but find that their impact is limited. These findings underscore the need to create more resilient LLMs that can maintain high performance across diverse prompts.

Self-playing Adversarial Language Game Enhances LLM Reasoning

We explore the self-play training procedure of large language models (LLMs) in a two-player adversarial language game called Adversarial Taboo. In this game, an attacker and a defender communicate with respect to a target word only visible to the attacker. The attacker aims to induce the defender to utter the target word unconsciously, while the defender tries to infer the target word from the attacker's utterances. To win the game, both players should have sufficient knowledge about the target word and high-level reasoning ability to infer and express in this information-reserved conversation. Hence, we are curious about whether LLMs' reasoning ability can be further enhanced by Self-Play in this Adversarial language Game (SPAG). With this goal, we let LLMs act as the attacker and play with a copy of itself as the defender on an extensive range of target words. Through reinforcement learning on the game outcomes, we observe that the LLMs' performance uniformly improves on a broad range of reasoning benchmarks. Furthermore, iteratively adopting this self-play process can continuously promote LLM's reasoning ability. The code is at https://github.com/Linear95/SPAG.

A Thorough Examination of Decoding Methods in the Era of LLMs

Decoding methods play an indispensable role in converting language models from next-token predictors into practical task solvers. Prior research on decoding methods, primarily focusing on task-specific models, may not extend to the current era of general-purpose large language models (LLMs). Moreover, the recent influx of decoding strategies has further complicated this landscape. This paper provides a comprehensive and multifaceted analysis of various decoding methods within the context of LLMs, evaluating their performance, robustness to hyperparameter changes, and decoding speeds across a wide range of tasks, models, and deployment environments. Our findings reveal that decoding method performance is notably task-dependent and influenced by factors such as alignment, model size, and quantization. Intriguingly, sensitivity analysis exposes that certain methods achieve superior performance at the cost of extensive hyperparameter tuning, highlighting the trade-off between attaining optimal results and the practicality of implementation in varying contexts.

Reasons to Reject? Aligning Language Models with Judgments

As humans, we consistently engage in interactions with our peers and receive feedback in the form of natural language. This language feedback allows us to reflect on our actions, maintain appropriate behavior, and rectify our errors. The question arises naturally: can we use language feedback to align large language models (LLMs)? In contrast to previous research that aligns LLMs with reward or preference data, we present the first systematic exploration of alignment through the lens of language feedback (i.e., judgment). We commence with an in-depth investigation of potential methods that can be adapted for aligning LLMs with judgments, revealing that these methods are unable to fully capitalize on the judgments. To facilitate more effective utilization of judgments, we propose a novel framework, Contrastive Unlikelihood Training (CUT), that allows for fine-grained inappropriate content detection and correction based on judgments. Our offline alignment results show that, with merely 1317 off-the-shelf judgment data, CUT (LLaMA2-13b) can beat the 175B DaVinci003 and surpass the best baseline by 52.34 points on AlpacaEval. The online alignment results demonstrate that CUT can align LLMs (LLaMA2-chat-13b) in an iterative fashion using model-specific judgment data, with a steady performance improvement from 81.09 to 91.36 points on AlpacaEval. Our analysis further suggests that judgments exhibit greater potential than rewards for LLM alignment and warrant future research.

Data-efficient Active Learning for Structured Prediction with Partial Annotation and Self-Training

In this work we propose a pragmatic method that reduces the annotation cost for structured label spaces using active learning. Our approach leverages partial annotation, which reduces labeling costs for structured outputs by selecting only the most informative substructures for annotation. We also utilize selftraining to incorporate the current model's automatic predictions as pseudo-labels for unannotated sub-structures. A key challenge in effectively combining partial annotation with self-training to reduce annotation cost is determining which sub-structures to select to label. To address this challenge we adopt an error estimator to decide the partial selection ratio adaptively according to the current model's capability. In evaluations spanning four structured prediction tasks, we show that our combination of partial annotation and self-training using an adaptive selection ratio reduces annotation cost over strong full annotation baselines under a fair comparison scheme that takes reading time into consideration.

A Survey of Active Learning for Natural Language Processing

In this work, we provide a survey of active learning (AL) for its applications in natural language processing (NLP). In addition to a fine-grained categorization of query strategies, we also investigate several other important aspects of applying AL to NLP problems. These include AL for structured prediction tasks, annotation cost, model learning (especially with deep neural models), and starting and stopping AL. Finally, we conclude with a discussion of related topics and future directions.

Towards More Efficient Insertion Transformer with Fractional Positional Encoding

Auto-regressive neural sequence models have been shown to be effective across text generation tasks. However, their left-to-right decoding order prevents generation from being parallelized. Insertion Transformer (Stern et al., 2019) is an attractive alternative that allows outputting multiple tokens in a single generation step. Nevertheless, due to the incompatibility of absolute positional encoding and insertion-based generation schemes, it needs to refresh the encoding of every token in the generated partial hypotheses at each step, which could be costly. We design a novel incremental positional encoding scheme for insertion transformers called Fractional Positional Encoding (FPE), which allows reusing representations calculated in previous steps. Empirical studies on various language generation tasks demonstrate the effectiveness of FPE, which leads to reduction of floating point operations and latency improvements on batched decoding.